dspy-finetune-bootstrap

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill's RAG pipeline (RAGClassifier) uses dspy.Retrieve / ColBERTv2 (pointing at http://20.102.90.50:2017/wiki17_abstracts) to fetch public passages and then feeds those retrieved passages as context into the model's chain-of-thought, so the agent directly reads and interprets untrusted third-party content.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill configures a runtime ColBERT retriever at http://20.102.90.50:2017/wiki17_abstracts which will fetch external passages that are directly injected into model context/prompts during execution, making it a required runtime dependency that can control agent behavior.